annahdo / implementing_activation_steering
A collection of different ways to implement accessing and modifying internal model activations for LLMs
☆14Updated 6 months ago
Alternatives and similar repositories for implementing_activation_steering:
Users that are interested in implementing_activation_steering are comparing it to the libraries listed below
- Experiments with representation engineering☆11Updated last year
- Measuring the situational awareness of language models☆34Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆92Updated last year
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 10 months ago
- ☆30Updated 11 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆17Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆52Updated 5 months ago
- Sparse Autoencoder Training Library☆48Updated 5 months ago
- ☆26Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆94Updated last month
- ☆27Updated 8 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆68Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆167Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆63Updated 3 weeks ago
- ☆35Updated last month
- Algebraic value editing in pretrained language models☆63Updated last year
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆11Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 10 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆143Updated 10 months ago
- A library for mechanistic anomaly detection☆21Updated 3 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆43Updated 6 months ago
- Applying SAEs for fine-grained control☆17Updated 4 months ago
- ☆24Updated 3 months ago
- ☆23Updated last month
- ☆121Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago